TensorRT-LLMs/tests/unittest/_torch/speculative
Kaiyu Xie b4e5df0ee0
Breaking change: perf: Enable scheduling overlap by default (#4174)
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
2025-05-15 14:27:36 +08:00
..
test_eagle3.py Breaking change: perf: Enable scheduling overlap by default (#4174) 2025-05-15 14:27:36 +08:00
test_mtp_prepare_drafter_inputs.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_mtp_sample_and_accept_draft_tokens.py [fix] Fix relaxed acceptance to support enabling it in context phase (#4126) 2025-05-09 14:11:14 +08:00
test_mtp_update_mtp_hidden_states.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00